Related papers: Neural B-Frame Coding: Tackling Domain Shift Issue…

Recently,the detection transformer has gained substantial attention for its inherent minimal post-processing requirement.However,this paradigm relies on abundant training data,yet in the context of the cross-domain adaptation,insufficient…

This paper introduces a new method for inter-frame coding based on two complementary autoencoders: MOFNet and CodecNet. MOFNet aims at computing and conveying the Optical Flow and a pixel-wise coding Mode selection. The optical flow is used…

The prior self-supervised learning researches mainly select image-level instance discrimination as pretext task. It achieves a fantastic classification performance that is comparable to supervised learning methods. However, with degraded…

Overparameterization and overfitting are common concerns when designing and training deep neural networks, that are often counteracted by pruning and regularization strategies. However, these strategies remain secondary to most learning…

Scaling feature values is an important step in numerous machine learning tasks. Different features can have different value ranges and some form of a feature scaling is often required in order to learn an accurate classifier. However,…

We propose a test-time adaptation method for cross-domain image segmentation. Our method is simple: Given a new unseen instance at test time, we adapt a pre-trained model by conducting instance-specific BatchNorm (statistics) calibration.…

Class imbalance poses a significant challenge to supervised classification, particularly in critical domains like medical diagnostics and anomaly detection where minority class instances are rare. While numerous studies have explored…

Existing transfer learning-based beam prediction approaches primarily rely on simple fine-tuning. When there is a significant difference in data distribution between the target domain and the source domain, simple fine-tuning limits the…

Classification with a large number of classes is a key problem in machine learning and corresponds to many real-world applications like tagging of images or textual documents in social networks. If one-vs-all methods usually reach top…

We introduce BEACON--Best-Effort Adaptation for Cross-Domain Co-Training--a theory-driven framework for training generative robot policies with abundant source demonstrations and limited target demonstrations. BEACON casts cross-domain…

Convolution neural networks have achieved remarkable performance in many tasks of computing vision. However, CNN tends to bias to low frequency components. They prioritize capturing low frequency patterns which lead them fail when suffering…

Cross-domain object detection has recently attracted more and more attention for real-world applications, since it helps build robust detectors adapting well to new environments. In this work, we propose an end-to-end solution based on…

Few-shot learning aims to generalize to novel classes with only a few samples with class labels. Research in few-shot learning has borrowed techniques from transfer learning, metric learning, meta-learning, and Bayesian methods. These…

Most standard learning approaches lead to fragile models which are prone to drift when sequentially trained on samples of a different nature - the well-known "catastrophic forgetting" issue. In particular, when a model consecutively learns…

As deep neural networks are increasingly deployed in dynamic, real-world environments, relying on a single static model is often insufficient. Changes in input data distributions caused by sensor drift or lighting variations necessitate…

Neural rankers based on deep pretrained language models (LMs) have been shown to improve many information retrieval benchmarks. However, these methods are affected by their the correlation between pretraining domain and target domain and…

The use of high-dimensional features has become a normal practice in many computer vision applications. The large dimension of these features is a limiting factor upon the number of data points which may be effectively stored and processed,…

The existing image captioning approaches typically train a one-stage sentence decoder, which is difficult to generate rich fine-grained descriptions. On the other hand, multi-stage image caption model is hard to train due to the vanishing…

Improving model's generalizability against domain shifts is crucial, especially for safety-critical applications such as autonomous driving. Real-world domain styles can vary substantially due to environment changes and sensor noises, but…

Overfitting in deep learning has been the focus of a number of recent works, yet its exact impact on the behavior of neural networks is not well understood. This study analyzes overfitting by examining how the distribution of logits alters…