Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks126 from public data
- 6,705
- BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning3,255
This work constructs BDD100K, the largest driving video dataset with 100K videos and 10 tasks to evaluate the exciting progress of image recognition algorithms on autonomous driving and shows that special training strategies are needed for existing models to perform such heterogeneous tasks.
- RePaint: Inpainting using Denoising Diffusion Probabilistic Models2,341
This work proposes RePaint: A Denoising Diffusion Probabilistic Model (DDPM) based inpainting approach that is applicable to even extreme masks and outperforms state-of-the-art Autoregressive, and GAN approaches for at least five out of six mask distributions.
- 2,329
- Dilated Residual Networks1,841
It is shown that dilated residual networks (DRNs) outperform their non-dilated counterparts in image classification without increasing the models depth or complexity and the accuracy advantage of DRNs is further magnified in downstream applications such as object localization and semantic segmentation.
- 1,623
- Deep Layer Aggregation1,568
This work augments standard architectures with deeper aggregation to better fuse information across layers and iteratively and hierarchically merge the feature hierarchy to make networks with better accuracy and fewer parameters.
- 1,484
- Semantic Scene Completion from a Single Depth Image1,453
The semantic scene completion network (SSCNet) is introduced, an end-to-end 3D convolutional network that takes a single depth image as input and simultaneously outputs occupancy and semantic labels for all voxels in the camera view frustum.
- 1,246
- BDD100K: A Diverse Driving Video Database with Scalable Annotation Tooling.977
The design and implementation of a scalable annotation system that can provide a comprehensive set of image labels for large-scale driving datasets, and a new driving dataset, which is an order of magnitude larger than previous efforts.
- Scaling Vision Transformers to 22 Billion Parameters961
A recipe for highly efficient and stable training of a 22B-parameter ViT (ViT-22B) and a wide variety of experiments on the resulting model, which demonstrates the potential for "LLM-like"scaling in vision, and provides key steps towards getting there.
- End-to-End Learning of Driving Models from Large-Scale Video Datasets889
This work advocates learning a generic vehicle motion model from large scale crowd-sourced video data, and develops an end-to-end trainable architecture for learning to predict a distribution over future vehicle egomotion from instantaneous monocular camera observations and previous vehicle state.
- Few-Shot Object Detection via Feature Reweighting879
This work develops a few-shot object detector that can learn to detect novel objects from only a few annotated examples, using a meta feature learner and a reweighting module within a one-stage detection architecture.
- SkipNet: Learning Dynamic Routing in Convolutional Networks813
This work introduces SkipNet, a modified residual network, that uses a gating network to selectively skip convolutional blocks based on the activations of the previous layer, and proposes a hybrid learning algorithm that combines supervised learning and reinforcement learning to address the challenges of non-differentiable skipping decisions.
- Segment Anything in High Quality714
A learnable High-Quality Output Token is injected into SAM's mask decoder and is responsible for predicting the high-quality mask, which reuses and preserves the pre-trained model weights of SAM, while only introducing minimal additional parameters and computation.
- 602
- Exploring Cross-Image Pixel Contrast for Semantic Segmentation596
This work raises a pixel-wise metric learning paradigm for semantic segmentation, by explicitly exploring the structures of labeled pixels, which were rarely explored before, and hopes this work will encourage the community to rethink the current de facto training paradigm in semantic segmentsation.
- Scribbler: Controlling Deep Image Synthesis with Sketch and Color535
A deep adversarial image synthesis architecture that is conditioned on sketched boundaries and sparse color strokes to generate realistic cars, bedrooms, or faces is proposed and demonstrates a sketch based image synthesis system which allows users to scribble over the sketch to indicate preferred color for objects.
- UniDepth: Universal Monocular Metric Depth Estimation523
This work proposes a new model, UniDepth, capable of reconstructing metric 3D scenes from solely single images across domains, and proposes a geometric invariance loss that promotes the invariance of camera-prompted depth features.
- Quasi-Dense Similarity Learning for Multiple Object Tracking513
Quasi-Dense Similarity Learning is presented, which densely samples hundreds of region proposals on a pair of images for contrastive learning and which outperforms all existing methods on MOT, BDD100K, Waymo, and TAO tracking benchmarks.
- Dual Aggregation Transformer for Image Super-Resolution455
A novel Transformer model, Dual Aggregation Transformer (DAT), is proposed, which aggregates features across spatial and channel dimensions, in the inter-block and intra-block dual manner.
- Unifying Flow, Stereo and Depth Estimation433
It is demonstrated that cross-attention enables integration of knowledge from another image via cross-view interactions, which greatly improves the quality of the extracted features and enables cross-task transfer.
- Transforming Model Prediction for Tracking433
This work trains the proposed tracker end-to-end and validate its performance by conducting comprehensive experiments on multiple tracking datasets, achieving an AUC of 68.5% on the challenging LaSOT [14] dataset.
- End-to-End Urban Driving by Imitating a Reinforcement Learning Coach358
A reinforcement learning expert is trained that maps bird’s-eye view images to continuous low-level actions and provides in-formative supervision signals for imitation learning agents to learn from that achieves expert-level performance.
- TextureGAN: Controlling Deep Image Synthesis with Texture Patches302
This paper is the first to examine texture control in deep image synthesis guided by sketch, color, and texture and develops a local texture loss in addition to adversarial and content loss to train the generative network.
- 296
- 290
- Hierarchical Discrete Distribution Decomposition for Match Density Estimation276
Hierarchical Discrete Distribution Decomposition (HD^3), a framework suitable for learning probabilistic pixel correspondences in both optical flow and stereo matching, is proposed and achieves state-of-the-art results.
- SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptation273
This paper introduces the largest multi-task synthetic dataset for autonomous driving, SHIFT, which presents discrete and continuous shifts in cloudiness, rain and fog intensity, time of day, and vehicle and pedestrian density.
- Joint Monocular 3D Vehicle Detection and Tracking250
A novel online framework for 3D vehicle detection and tracking from monocular videos that can not only associate detections of vehicles in motion over time, but also estimate their complete 3D bounding box information from a sequence of 2D images captured on a moving platform.
- Generative Cooperative Learning for Unsupervised Video Anomaly Detection236
This work proposes a novel unsupervised Generative Cooperative Learning (GCL) approach for video anomaly detection that exploits the low frequency of anomalies towards building a cross-supervision between a generator and a discriminator.
- LiDAR Snowfall Simulation for Robust 3D Object Detection196
This paper proposes a physically based method to simulate the effect of snowfall on real clear-weather LiDAR point clouds, and conducts an extensive evaluation using several state-of-the-art 3D object detection methods to show that this simulation consistently yields significant performance gains on the real snowy STF dataset.
- 192
- QDTrack: Quasi-Dense Similarity Learning for Appearance-Only Multiple Object Tracking173
This paper presents Quasi-Dense Similarity Learning, which densely samples hundreds of object regions on a pair of images for contrastive learning, and combines this similarity learning with multiple existing object detectors to build QDTrack, which rivals the performance of state-of-the-art tracking methods on all benchmarks.
- Mask Transfiner for High-Quality Instance Segmentation173
This paper presents Mask Transfiner, a transformer-based approach to instance segmentation that decomposes and represents the image regions as a quadtree, allowing it to predict highly accurate instance masks, at a low computational cost.
- Monocular Quasi-Dense 3D Object Tracking162
This work proposes a framework that can effectively associate moving objects over time and estimate their full 3D bounding box information from a sequence of 2D images captured on a moving platform and an LSTM-based object velocity learning module aggregates the long-term trajectory information for more accurate motion extrapolation.
- iDisc: Internal Discretization for Monocular Depth Estimation137
iDisc, a new module, implements a continuous-discrete-continuous bottleneck to learn internal discretized representations without supervision, and sets the new state of the art with significant improvements on NYU-Depth v2 and KittI, outperforming all published methods on the official KITTI benchmark.
- Strategic Preys Make Acute Predators: Enhancing Camouflaged Object Detectors by Generating Camouflaged Objects134
An adversarial training framework is proposed, Camouflageator, which introduces an auxiliary generator to generate more camouflaged objects that are harder for a COD method to detect and ICEG, which brings state-of-the-art COD performance.
- 130
- Segment Anything Meets Point Tracking119
This paper introduces SAM-PT, an innovative method for point-centric video segmentation, leveraging the capabilities of SAM alongside long-term point tracking, and uniquely exploits point propagation to utilize local structure information independent of object semantics.
- SAGA: Stochastic Whole-Body Grasping with Contact118
The effectiveness of the SAGA method is demonstrated, which is a novel generative framework to synthesize realistic and expressive whole-body motions that approach and grasp randomly placed unseen objects.
- TAFE-Net: Task-Aware Feature Embeddings for Low Shot Learning116
This work proposes Task Aware Feature Embedding Networks (TAFE-Nets) to learn how to adapt the image representation to a new task in a meta learning fashion and shows that TAFE-Net is highly effective in generalizing to new tasks or concepts.
- Uncertainty Guided Policy for Active Robotic 3D Reconstruction Using Neural Radiance Fields115
A ray-based volumetric uncertainty estimator, which computes the entropy of the weight distribution of the color samples along each ray of the object's implicit neural representation, and shows that it is possible to infer the uncertainty of the underlying 3D geometry given a novel view with the proposed estimator.
- Deep Object-Centric Policies for Autonomous Driving109
A taxonomy of “object-centric” models which leverage both object instances and end-to-end learning are described, showing that object-centric models outperform object-agnostic methods in scenes with other vehicles and pedestrians, even with an imperfect detector.
- SSCBench: A Large-Scale 3D Semantic Scene Completion Benchmark for Autonomous Driving107
This work introduces SSCBench, a comprehensive benchmark that integrates scenes from widely used automotive datasets and has unified semantic labels across diverse datasets to simplify cross-domain generalization testing.
- Characterizing Adversarial Examples Based on Spatial Consistency Information for Semantic Segmentation105
It is observed that spatial consistency information can be potentially leveraged to detect adversarial examples robustly even when a strong adaptive attacker has access to the model and detection strategies.
- 104
- Interactive 3D Modeling with a Generative Adversarial Network96
This work proposes the idea of using a generative adversarial network (GAN) to assist users in designing real-world shapes with a simple interface to assist novice users to create 3D models characteristic of the training data by only specifying rough edits.
- Disentangling Propagation and Generation for Video Prediction94
A computational model for high-fidelity video prediction which disentangles motion-specific propagation from motion-agnostic generation and introduces a confidence-aware warping operator which gates the output of pixel predictions from a flow predictor for non-occluded regions and from a context encoder for occluded regions.
- MuRF: Multi-Baseline Radiance Fields86
Multi-Baseline Radiance Fields (MuRF), a general feed-forward approach to solving sparse view syn-thesis under multiple different baseline settings, achieves state-of-the-art performance across multiple different baseline settings and diverse scenarios ranging from simple objects (DTU) to complex indoor and outdoor scenes.
- OVTrack: Open-Vocabulary Multiple Object Tracking86
OVTrack is developed, an open-vocabulary tracker that is capable of tracking arbitrary object classes and its design is based on two key ingredients, leveraging vision-language models for both classification and association via knowledge distillation and a data hallucination strategy for robust appearance feature learning from denoising diffusion probabilistic models.
- TrafficBots: Towards World Models for Autonomous Driving Simulation and Motion Prediction85
TrafficBots is presented, a multi-agent policy built upon motion prediction and end-to-end driving, and based on TrafficBots a world model tailored for the planning module of autonomous vehicles is obtained.
- 85
- QuantSR: Accurate Low-bit Quantization for Efficient Image Super-Resolution84
A novel quantized image SR network, called QuantSR, is proposed, which achieves accurate and efficient SR processing under low-bit quantization and introduces the Redistribution-driven Learnable Quantizer (RLQ), and the Depth-dynamic Quantized Architecture (DQA), which allows for the trade-off between efficiency and accuracy during inference through weight sharing.
- Matching Anything by Segmenting Anything83
This work proposes MASA, a novel method for robust instance association learning, capable of matching any objects within videos across diverse domains without tracking labels, Leveraging the rich object segmentation from the Segment Anything Model (SAM).
- Deep Reparametrization of Multi-Frame Super-Resolution and Denoising80
The deep reparametrization of the maximum a posteriori formulation commonly employed in multi-frame image restoration tasks is proposed, derived by introducing a learned error metric and a latent representation of the target image, which transforms the MAP objective to a deep feature space.
- 74
- 73
- 70
- Cascade-DETR: Delving into High-Quality Universal Object Detection69
Cascade-DETR is introduced for high-quality universal object detection, and the Cascade Attention layer is proposed, which explicitly integrates object-centric information into the detection decoder by limiting the attention to the previous box prediction.
- Warp Consistency for Unsupervised Learning of Dense Correspondences61
W warp consistency loss is proposed, an unsupervised learning objective for dense correspondence regression that is effective even in settings with large appearance and view-point changes and sets a new state of the art on several challenging benchmarks, including MegaDepth, RobotCar and TSS.
- HelpingHand61
This paper presents a data-driven approach for synthesizing the 6D hand gesture data for users of low-quality input devices and outputs a 6D trajectory that can be fed into any virtual brush stroke engine to make expressive strokes for novices or users of limited hardware.
- R3D3: Dense 3D Reconstruction of Dynamic Scenes from Multiple Cameras58
This work proposes R3D3, a multi-camera system for dense 3D reconstruction and ego-motion estimation that integrates multi- camera feature correlation and dense bundle adjustment operators that yield robust geometric depth and pose estimates, and introduces learnable scene priors via a depth refinement network.
- BiBench: Benchmarking and Analyzing Network Binarization57
This work presents BiBench, a rigorously designed benchmark with in-depth analysis for network binarization, and reveals that the binarized operator has a crucial impact on the performance and deployability ofbinarized networks.
- Automatic triage for a photo series54
A benchmark for measuring the effectiveness of algorithmic models of how people select photos is established, and several new approaches for modeling human preference based on machine learning are introduced.
- 53
- Large-Scale 3D Shape Retrieval from ShapeNet Core5552
This track aims to provide a benchmark to evaluate large-scale shape retrieval based on the ShapeNet dataset, using ShapeNet Core55, which provides more than 50 thousands models over 55 common categories in total for training and evaluating several algorithms.
- 46
- Maskomaly:Zero-Shot Mask Anomaly Segmentation45
A simple and practical framework for anomaly segmentation which builds upon mask-based standard semantic segmentation networks by adding a simple inference-time post-processing step which leverages the raw mask outputs of such networks.
- CC-3DT: Panoramic 3D Object Tracking via Cross-Camera Fusion43
This paper proposes a method for panoramic 3D object tracking that associates and models object trajectories both temporally and across views, and improves the overall tracking consistency, and sets a new state-of-the-art with 12.6% improvement in average multi-object tracking accuracy (AMOTA) among all camera-based methods on the competitive NuScenes 3D tracking benchmark.
- Probabilistic Warp Consistency for Weakly-Supervised Semantic Correspondences43
This work proposes Probabilistic Warp Consistency, a weakly-supervised learning objective for semantic matching that directly supervises the dense matching scores predicted by the network, encoded as a conditional probability distribution.
- MolGrapher: Graph-based Visual Recognition of Chemical Structures42
This work introduces MolGrapher to recognize chemical structures visually, and proposes a synthetic data generation pipeline producing diverse and realistic results.
- 42
- 40
- Learning Deep Sensorimotor Policies for Vision-Based Autonomous Drone Racing39
This method combines feature representation learning to extract task-relevant feature representations from high-dimensional image inputs with a learning-by-cheating framework to train a deep sensorimotor policy for vision-based drone racing, eliminating the need for globally-consistent state estimation, trajectory planning, and handcrafted control design.
- S$^{3}$M-Net: Joint Learning of Semantic Segmentation and Stereo Matching for Autonomous Driving38
This article introduces S3M-Net, a novel joint learning framework developed to perform semantic segmentation and stereo matching simultaneously and its superior performance compared to other state-of-the-art single-task networks.
- Robust Object Detection via Instance-Level Temporal Cycle Confusion37
This work introduces a novel self-supervised task, instance-level temporal cycle confusion (CycConf), which operates on the region features of the object detectors, and encourages the object detector to explore invariant structures across instances under various motions, which leads to improved model robustness in unseen domains at test time.
- 37
- 35
- Bitcoin-Enhanced Proof-of-Stake Security: Possibilities and Impossibilities35
The experimental results show that this delay can be reduced from weeks in existing PoS chains to less than 5 hours using Babylon, at a transaction cost of less than 10K USD per annum for posting the checkpoints onto Bitcoin.
- 35
- Mask-Free Video Instance Segmentation32
This work proposes MaskFreeVIS, achieving highly competitive VIS performance, while only using bounding box annotations for the object state, by introducing the Temporal KNN-patch Loss (TK-Loss), providing strong mask supervision without any labels.
- BiMatting: Efficient Video Matting via Binarization28
BiMatting is proposed, an accurate and efficient video matting model using binarization that outperforms other binarized video matting models, including state-of-the-art (SOTA) binarization methods, by a significant margin and performs comparably to the full-precision counterpart in visual quality.
- 26
- Video OWL-ViT: Temporally-consistent open-world localization in video24
This work presents an architecture and a training recipe that adapts pretrained open-world image models to localization in videos and demonstrates that open-world capabilities, learned from large-scale image-text pretraining, can be transferred successfully to open-world localization across diverse videos.
- Condition-Invariant Semantic Segmentation22
This work proposes to leverage stylization in performing feature-level adaptation by aligning the internal network features extracted by the encoder of the network from the original and the stylized view of each input image with a novel feature invariance loss.
- PatCID: an open-access dataset of chemical structures in patent documents22
Leveraging state-of-the-art methods of document understanding, PatCID high-quality data outperforms currently available automatically-generated patent-databases and even competes with proprietary manually-created patent-databases.
- DARTH: Holistic Test-time Adaptation for Multiple Object Tracking21
This paper proposes a detection consistency formulation to adapt object detection in a self-supervised fashion, while adapting the instance appearance representations via the authors' novel patch contrastive loss.
- 21
- Spatio-Temporal Action Detection Under Large Motion20
This work finds that track-aware feature aggregation consistently achieves a large improvement in action detection performance, especially for actions under large motion compared to cuboid-aware baseline, and reports state-of-the-art on the large-scale MultiSports dataset.
- ICGNet: A Unified Approach for Instance-Centric Grasping18
An end-to-end architecture for object-centric grasping that uses pointcloud data from a single arbitrary viewing direction as an input and generates an instance-centric representation for each partially observed object in the scene, used for object reconstruction and grasp detection in cluttered table-top scenes.
- Normalizing Flow as a Flexible Fidelity Objective for Photo-Realistic Super-resolution16
This work revisiting the L1 loss and showing that it corresponds to a one-layer conditional flow is shown to outperform state-of-the-art methods for photo-realistic super-resolution and demonstrate that the flexibility of deeper flows leads to better visual quality and consistency when combined with adversarial losses.
- 16
- Normalization Perturbation: A Simple Domain Generalization Method for Real-World Domain Shifts15
This work proposes to perturb the channel statistics of source domain features to synthesize various latent styles, so that the trained deep model can perceive diverse potential domains and generalizes well even without observations of target domain data in training.
- Pangu Ultra MoE: How to Train Your Big MoE on Ascend NPUs14
Extensive experiments indicate that the recipe uncovered can lead to efficient training of large-scale sparse language models with MoE, and the Ascend system is capable of harnessing all the training stages of the state-of-the-art language models.
- Distilling ODE Solvers of Diffusion Models into Smaller Steps12
Distilled-ODE solvers (D-ODE solvers) are introduced, a straightforward distillation approach grounded in ODE solver formulations that seamlessly integrates the strengths of both learning-free and learning-based sampling.
- Video Task Decathlon: Unifying Image and Video Tasks in Autonomous Driving12
This work designs a Curriculum training, Pseudo-labeling, and Fine-tuning scheme to successfully train VTDNet on all tasks and mitigate performance loss, and develops a unified network, VTDNet, that uses a single structure and a single set of weights for all ten tasks.
- Dense Prediction with Attentive Feature Aggregation10
Attentive Feature Aggregation is introduced to fuse different network layers with more expressive non-linear operations and improves the performance of the Deep Layer Aggregation model by nearly 6% mIoU on Cityscapes.
- TACS: Taxonomy Adaptive Cross-Domain Semantic Segmentation10
This work addresses the image-level domain gap by proposing an uncertainty-rectified contrastive learning method, leading to more domain-invariant and class-discriminative features, and outperforms the previous state-of-the-art by a large margin.
- Instance-Aware Predictive Navigation in Multi-Agent Environments10
The Instance-Aware Predictive Control approach is proposed, which forecasts interactions between agents as well as future scene structures, and a sequential action sampling strategy is designed to better leverage predicted states on both scene-level and instance-level.
- Quasi-Dense Instance Similarity Learning9
This paper presents a simple yet effective quasi-dense matching method to learn instance similarity from hundreds of region proposals in a pair of images, and can outperform existing methods without using location or motion heuristics on joint object detection and tracking.
- 9
- Uncertainty-Driven Dense Two-View Structure From Motion8
The proposed approach achieves remarkable depth accuracy and state-of-the-art camera pose results superseding SuperPoint and SuperGlue accuracy when tested on benchmark datasets such as DeMoN, YFCC100 M, and ScanNet.
- 8
- Multi-modal NeRF Self-Supervision for LiDAR Semantic Segmentation7
A Semi-Supervised Learning setup to leverage unlabeled LiDAR pointclouds alongside distilled knowledge from the camera images and shows the effectiveness of this approach in three public LiDAR Semantic Segmentation benchmarks: nuScenes, SemanticKITTI and ScribbleKITTI.
- DexDribbler: Learning Dexterous Soccer Manipulation via Dynamic Supervision7
It is observed that the learning scheme can not only make the policy network converge faster but also enable soccer robots to perform sophisticated maneuvers like sharp cuts and turns on flat surfaces, a capability that was lacking in previous methods.
- 7
- 6
- 5
- 5
- Composite Learning for Robust and Effective Dense Predictions4
It is found that jointly training a dense prediction task with a self-supervised (auxiliary) task can consistently improve the performance of the target task, while eliminating the need for labeling auxiliary tasks.
- Pangu Light: Weight Re-Initialization for Pruning and Accelerating LLMs3
Pangu Light is introduced, a framework for LLM acceleration centered around structured pruning coupled with novel weight re-initialization techniques designed to address this ``missing piece''.
- 2
- A Multiplicative Value Function for Safe and Efficient Reinforcement Learning2
This work proposes a safe model-free RL algorithm with a novel multiplicative value function consisting of a safety critic and a reward critic, and integrates this approach into two popular RL algorithms, Proximal Policy Optimization and Soft Actor-Critic.
- 3DPPE: 3D Point Positional Encoding for Multi-Camera 3D Object Detection Transformers2
3D point PE with estimated 3D point locations can bring significant improvements compared to the commonly used camera-ray PE and is shown to have superior performance since more precise positioning may lead to superior 3D detection.
- 2
- 2
- 1
- Fast Hierarchical Learning for Few-Shot Object Detection1
This work poses few-shot detection as a hierarchical learning problem, where the novel classes are treated as the child classes of existing base classes and the background class, leading to significantly lower training times compared to stochastic gradient descent.
- Task-Aware Deep Sampling for Feature Generation.1
This work proposes a sample efficient learning model composed of a TDS generator, a discriminator and a classifier (e.g., a soft-max classifier) and finds that this model achieves state-of-the-art results on the compositional zero- shot learning benchmarks as well as improving upon the established benchmarks in conventional zero-shot learning with a faster convergence rate.
- TAFE-Net: Task-Aware Feature Embeddings for Efficient Learning and Inference.1
This work proposes Task-Aware Feature Embedding Networks (TAFE-Nets) to learn how to adapt the image representation to a new task in a meta-learning fashion and shows that the TAFE-Net is highly effective in generalizing to new tasks or concepts and offers efficient prediction with low computational cost.
- 1
- DVPSFormer: Efficient Online Depth-aware Video Panoptic Segmentation for Autonomous Driving–
DVPSFormer is proposed, a unified online architecture designed for efficient 4D scene understanding that establishes a new state-of-the-art on the Cityscapes-DVPS and SemKITTI-DVPS benchmarks, offering a streamlined solution for online robotic perception.
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-14. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.