Eliminating Exposure Bias and Metric Mismatch in Multiple Object Tracking
Identity Switching remains one of the main difficulties Multiple Object Tracking (MOT) algorithms have to deal with. Many state-of-the-art approaches now use sequence models to solve this problem but their training can be affected by biases that decrease their efficiency. In this paper, we introduce a new training procedure that confronts the algorithm to its own mistakes while explicitly attempting to minimize the number of switches, which results in better training. We propose an iterative scheme of building a rich training set and using it to learn a scoring function that is an explicit proxy for the target tracking metric. Whether using only simple geometric features or more sophisticated ones that also take appearance into account, our approach outperforms the state-of-the-art on several MOT benchmarks.
Code (0)
등록된 구현이 없습니다.
Tasks
Multiple Object TrackingObject TrackingSimilar Papers 제목 키워드 기반
Eliminating Exposure Bias and Loss-Evaluation Mismatch in Multiple Object Tracking
Identity Switching remains one of the main difficulties Multiple Object Tracking (MOT) algorithms have to deal with. Many state-of-the-art approaches now use sequence models to solve this problem but their training can b…
Multiple Object TrackingObject TrackingElucidating the Exposure Bias in Diffusion Models
Diffusion models have demonstrated impressive generative capabilities, but their \textit{exposure bias} problem, described as the input mismatch between training and sampling, lacks in-depth exploration. In this paper, w…
AttributeImage GenerationWhy Exposure Bias Matters: An Imitation Learning Perspective of Error Accumulation in Language Generation
Current language generation models suffer from issues such as repetition, incoherence, and hallucinations. An often-repeated hypothesis is that this brittleness of generation models is caused by the training and the gene…
Imitation LearningText GenerationText Generation by Learning from Demonstrations
Current approaches to text generation largely rely on autoregressive models and maximum likelihood estimation. This paradigm leads to (i) diverse but low-quality samples due to mismatched learning objective and evaluatio…
Machine TranslationQuestion GenerationQuestion-GenerationReinforcement Learning (RL)+2Reducing Exposure Bias in Training Recurrent Neural Network Transducers
When recurrent neural network transducers (RNNTs) are trained using the typical maximum likelihood criterion, the prediction network is trained only on ground truth label sequences. This leads to a mismatch during infere…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Language ModelingLanguage Modelling+2