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.
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.