Related papers: ETran: Energy-Based Transferability Estimation

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…

The visual representation of a pre-trained model prioritizes the classifiability on downstream tasks, while the widespread applications for pre-trained visual models have posed new requirements for representation interpretability. However,…

We study how the training data distribution affects confidence and performance in image classification models. We introduce Embedding Density, a model-agnostic framework that estimates prediction confidence by measuring the distance of test…

Detecting Out-of-Domain (OOD) or unknown intents from user queries is essential in a task-oriented dialog system. Traditional softmax-based confidence scores are susceptible to the overconfidence issue. In this paper, we propose a simple…

Efficient learning from demonstration for long-horizon tasks remains an open challenge in robotics. While significant effort has been directed toward learning trajectories, a recent resurgence of object-centric approaches has demonstrated…

Adversarial examples have been demonstrated to threaten many computer vision tasks including object detection. However, the existing attacking methods for object detection have two limitations: poor transferability, which denotes that the…

Unknown intent detection aims to identify the out-of-distribution (OOD) utterance whose intent has never appeared in the training set. In this paper, we propose using energy scores for this task as the energy score is theoretically aligned…

With the preponderance of pretrained deep learning models available off-the-shelf from model banks today, finding the best weights to fine-tune to your use-case can be a daunting task. Several methods have recently been proposed to find…

Clothing segmentation and fine-grained attribute recognition are challenging tasks at the crossing of computer vision and fashion, which segment the entire ensemble clothing instances as well as recognize detailed attributes of the clothing…

Recent self-supervised pretraining methods for object detection largely focus on pretraining the backbone of the object detector, neglecting key parts of detection architecture. Instead, we introduce DETReg, a new self-supervised method…

Today, deep learning is increasingly applied in security-critical situations such as autonomous driving and medical diagnosis. Despite its success, the behavior and robustness of deep networks are not fully understood yet, posing a…

With the growth of the academic engines, the mining and analysis acquisition of massive researcher data, such as collaborator recommendation and researcher retrieval, has become indispensable. It can improve the quality of services and…

A critical object detection task is finetuning an existing model to detect novel objects, but the standard workflow requires bounding box annotations which are time-consuming and expensive to collect. Weakly supervised object detection…

Ionic mobility determines the rate performance of several applications, such as batteries, fuel cells, and electrochemical sensors and is exponentially dependent on the migration barrier ($E_m$), a difficult to measure/calculate quantity.…

In this paper, we tackle the copy-paste image-to-image composition problem with a focus on object placement learning. Prior methods have leveraged generative models to reduce the reliance for dense supervision. However, this often limits…

Autonomous driving has achieved rapid development over the last few decades, including the machine perception as an important issue of it. Although object detection based on conventional cameras has achieved remarkable results in 2D/3D,…

Pre-trained Transformer-based models were reported to be robust in intent classification. In this work, we first point out the importance of in-domain out-of-scope detection in few-shot intent recognition tasks and then illustrate the…

Transfer learning, which allows a source task to affect the inductive bias of the target task, is widely used in computer vision. The typical way of conducting transfer learning with deep neural networks is to fine-tune a model pre-trained…

Deep learning models frequently make incorrect predictions with high confidence when presented with test examples that are not well represented in their training dataset. We propose a novel and straightforward approach to estimate…

Aided target recognition (AiTR), the problem of classifying objects from sensor data, is an important problem with applications across industry and defense. While classification algorithms continue to improve, they often require more…