Related papers: A Ranking-based, Balanced Loss Function Unifying C…

We introduce a new principle for model selection in regression and classification. Many regression models are controlled by some smoothness or flexibility or complexity parameter c, e.g. the number of neighbors to be averaged over in k…

Pairwise ranking methods are the basis of many widely used discriminative training approaches for structure prediction problems in natural language processing(NLP). Decomposing the problem of ranking hypotheses into pairwise comparisons…

In this paper, we propose SubLoRA, a rank determination method for Low-Rank Adaptation (LoRA) based on submodular function maximization. In contrast to prior approaches, such as AdaLoRA, that rely on first-order (linearized) approximations…

We consider the problem of Learning from Label Proportions (LLP), a weakly supervised classification setup where instances are grouped into "bags", and only the frequency of class labels at each bag is available. Albeit, the objective of…

Counterfactual learning to rank (CLTR) relies on exposure-based inverse propensity scoring (IPS), a LTR-specific adaptation of IPS to correct for position bias. While IPS can provide unbiased and consistent estimates, it often suffers from…

Machine learning classification tasks often benefit from predicting a set of possible labels with confidence scores to capture uncertainty. However, existing methods struggle with the high-dimensional nature of the data and the lack of…

Climate-induced disasters are and will continue to be on the rise, and thus search-and-rescue (SAR) operations, where the task is to localize and assist one or several people who are missing, become increasingly relevant. In many cases the…

We propose a new approach for the problem of relative depth estimation from a single image. Instead of directly regressing over depth scores, we formulate the problem as estimation of a probability distribution over depth and aim to learn…

Absolute Pose Regressors (APRs) directly estimate camera poses from monocular images, but their accuracy is unstable for different queries. Uncertainty-aware APRs provide uncertainty information on the estimated pose, alleviating the impact…

The conventional detectors tend to make imbalanced classification and suffer performance drop, when the distribution of the training data is severely skewed. In this paper, we propose to use the mean classification score to indicate the…

Parameter-efficient fine-tuning (PEFT) methods, such as LoRA, offer compact and effective alternatives to full model fine-tuning by introducing low-rank updates to pre-trained weights. However, most existing approaches rely on global low…

RetinaNet proposed Focal Loss for classification task and improved one-stage detectors greatly. However, there is still a gap between it and two-stage detectors. We analyze the prediction of RetinaNet and find that the misalignment of…

LiDAR-based place recognition (LPR) plays a pivotal role in autonomous driving, which assists Simultaneous Localization and Mapping (SLAM) systems in reducing accumulated errors and achieving reliable localization. However, existing reviews…

Repetitive action counting (RAC) aims to estimate the number of class-agnostic action occurrences in a video without exemplars. Most current RAC methods rely on a raw frame-to-frame similarity representation for period prediction. However,…

Large-scale reinforcement learning with verifiable rewards (RLVR) has demonstrated its effectiveness in harnessing the potential of large language models (LLMs) for single-turn reasoning tasks. In realistic reasoning scenarios, LLMs can…

Compared with model architectures, the training process, which is also crucial to the success of detectors, has received relatively less attention in object detection. In this work, we carefully revisit the standard training practice of…

Visual Place Recognition (VPR) determines a query image's geographic location by matching it against geotagged databases. However, existing methods struggle with perceptual aliasing caused by irrelevant regions and inefficient re-ranking…

Active learning - a class of algorithms that iteratively searches for the most informative samples to include in a training dataset - has been shown to be effective at annotating data for image classification. However, the use of active…

Multi-label learning is a challenging computer vision task that requires assigning multiple categories to each image. However, fully annotating large-scale datasets is often impractical due to high costs and effort, motivating the study of…

Tool-integrated (TI) reinforcement learning (RL) enables large language models (LLMs) to perform multi-step reasoning by interacting with external tools such as search engines and retrievers. Group Relative Policy Optimization (GRPO),…