35 citations · 321 across the 48 of their papers we have counts for
13 papers · 1 filter
Searching Parameterized AP Loss for Object Detection
Chenxin Tao, Zizhang Li, Xizhou Zhu +3
Loss functions play an important role in training deep-network-based object detectors. The most widely used evaluation metric for object detection is Average Precision (AP), which…
Temporal-Spatial Causal Interpretations for Vision-Based Reinforcement Learning
Wenjie Shi, Gao Huang, Shiji Song +1
Deep reinforcement learning (RL) agents are becoming increasingly proficient in a range of complex control tasks. However, the agent's behavior is usually difficult to interpret du…
AdaFocus V2: End-to-End Training of Spatial Dynamic Networks for Video Recognition
Yulin Wang, Yang Yue, Yuanze Lin +6
Recent works have shown that the computational efficiency of video recognition can be significantly improved by reducing the spatial redundancy. As a representative work, the adapt…
Exploring the Equivalence of Siamese Self-Supervised Learning via A Unified Gradient Framework
Chenxin Tao, Honghui Wang, Xizhou Zhu +4
Self-supervised learning has shown its great potential to extract powerful visual representations without human annotations. Various works are proposed to deal with self-supervised…
On the Integration of Self-Attention and Convolution
Xuran Pan, Chunjiang Ge, Rui Lu +4
Convolution and self-attention are two powerful techniques for representation learning, and they are usually considered as two peer approaches that are distinct from each other. In…
Fine-Grained Few Shot Learning with Foreground Object Transformation
Chaofei Wang, Shiji Song, Qisen Yang +2
Traditional fine-grained image classification generally requires abundant labeled samples to deal with the low inter-class variance but high intra-class variance problem. However,…
CAM-loss: Towards Learning Spatially Discriminative Feature Representations
Chaofei Wang, Jiayu Xiao, Yizeng Han +3
The backbone of traditional CNN classifier is generally considered as a feature extractor, followed by a linear layer which performs the classification. We propose a novel loss fun…
On the Power of Multitask Representation Learning in Linear MDP
Rui Lu, Gao Huang, Simon S. Du
While multitask representation learning has become a popular approach in reinforcement learning (RL), theoretical understanding of why and when it works remains limited. This paper…
Believe What You See: Implicit Constraint Approach for Offline Multi-Agent Reinforcement Learning
Yiqin Yang, Xiaoteng Ma, Chenghao Li +5
Learning from datasets without interaction with environments (Offline Learning) is an essential step to apply Reinforcement Learning (RL) algorithms in real-world scenarios. Howeve…
Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognition
Yulin Wang, Rui Huang, Shiji Song +2
Vision Transformers (ViT) have achieved remarkable success in large-scale image recognition. They split every 2D image into a fixed number of patches, each of which is treated as a…
Adaptive Focus for Efficient Video Recognition
Yulin Wang, Zhaoxi Chen, Haojun Jiang +3
In this paper, we explore the spatial redundancy in video recognition with the aim to improve the computational efficiency. It is observed that the most informative region in each…
CondenseNet V2: Sparse Feature Reactivation for Deep Networks
Le Yang, Haojun Jiang, Ruojin Cai +4
Reusing features in deep networks through dense connectivity is an effective way to achieve high computational efficiency. The recent proposed CondenseNet has shown that this mecha…
AutoLoss-Zero: Searching Loss Functions from Scratch for Generic Tasks
Hao Li, Tianwen Fu, Jifeng Dai +3
Significant progress has been achieved in automating the design of various components in deep networks. However, the automatic design of loss functions for generic tasks with vario…