CAPEEN: Image Captioning with Early Exits and Knowledge Distillation

• URL: http://arxiv.org/abs/2410.04433v1
• Date: Sun, 6 Oct 2024 10:05:01 GMT
• Title: CAPEEN: Image Captioning with Early Exits and Knowledge Distillation
• Authors: Divya Jyoti Bajpai, Manjesh Kumar Hanawal,
• Abstract summary: Deep neural networks (DNNs) have made significant progress in recognizing visual elements and generating descriptive text in image-captioning tasks. EE strategies can be used to enhance their efficiency, but their adaptation presents challenges in image captioning as it requires varying levels of semantic information for accurate predictions. We introduce CAPEEN to improve the performance of EE strategies using knowledge distillation.
• Score: 5.402030962296633
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep neural networks (DNNs) have made significant progress in recognizing visual elements and generating descriptive text in image-captioning tasks. However, their improved performance comes from increased computational burden and inference latency. Early Exit (EE) strategies can be used to enhance their efficiency, but their adaptation presents challenges in image captioning as it requires varying levels of semantic information for accurate predictions. To overcome this, we introduce CAPEEN to improve the performance of EE strategies using knowledge distillation. Inference in CAPEEN is completed at intermediary layers if prediction confidence exceeds a predefined value learned from the training data. To account for real-world deployments, where target distributions could drift from that of training samples, we introduce a variant A-CAPEEN to adapt the thresholds on the fly using Multiarmed bandits framework. Experiments on the MS COCO and Flickr30k datasets show that CAPEEN gains speedup of 1.77x while maintaining competitive performance compared to the final layer, and A-CAPEEN additionally offers robustness against distortions. The source code is available at https://github.com/Div290/CapEEN

Related papers

• Make Prompts Adaptable: Bayesian Modeling for Vision-Language Prompt Learning with Data-Dependent Prior [14.232144691524528]
  Recent Vision-Language Pretrained models have become the backbone for many downstream tasks. MLE training can lead the context vector to over-fit dominant image features in the training data. This paper presents a Bayesian-based framework of prompt learning, which could alleviate the overfitting issues on few-shot learning application.
  arXiv  Detail & Related papers  (2024-01-09T10:15:59Z)
• Value Explicit Pretraining for Learning Transferable Representations [11.069853883599102]
  We propose a method that learns generalizable representations for transfer reinforcement learning. We learn new tasks that share similar objectives as previously learned tasks, by learning an encoder for objective-conditioned representations. Experiments using a realistic navigation simulator and Atari benchmark show that the pretrained encoder produced by our method outperforms current SoTA pretraining methods.
  arXiv  Detail & Related papers  (2023-12-19T17:12:35Z)
• ALIP: Adaptive Language-Image Pre-training with Synthetic Caption [78.93535202851278]
  Contrastive Language-Image Pre-training (CLIP) has significantly boosted the performance of various vision-language tasks. The presence of intrinsic noise and unmatched image-text pairs in web data can potentially affect the performance of representation learning. We propose an Adaptive Language-Image Pre-training (ALIP), a bi-path model that integrates supervision from both raw text and synthetic caption.
  arXiv  Detail & Related papers  (2023-08-16T15:19:52Z)
• Simple Token-Level Confidence Improves Caption Correctness [117.33497608933169]
  Token-Level Confidence, or TLC, is a simple yet surprisingly effective method to assess caption correctness. We fine-tune a vision-language model on image captioning, input an image and proposed caption to the model, and aggregate token confidences over words or sequences to estimate image-caption consistency.
  arXiv  Detail & Related papers  (2023-05-11T17:58:17Z)
• Understanding and Mitigating Overfitting in Prompt Tuning for Vision-Language Models [108.13378788663196]
  We propose Subspace Prompt Tuning (SubPT) to project the gradients in back-propagation onto the low-rank subspace spanned by the early-stage gradient flow eigenvectors during the entire training process. We equip CoOp with Novel Learner Feature (NFL) to enhance the generalization ability of the learned prompts onto novel categories beyond the training set.
  arXiv  Detail & Related papers  (2022-11-04T02:06:22Z)
• Efficient Few-Shot Object Detection via Knowledge Inheritance [62.36414544915032]
  Few-shot object detection (FSOD) aims at learning a generic detector that can adapt to unseen tasks with scarce training samples. We present an efficient pretrain-transfer framework (PTF) baseline with no computational increment. We also propose an adaptive length re-scaling (ALR) strategy to alleviate the vector length inconsistency between the predicted novel weights and the pretrained base weights.
  arXiv  Detail & Related papers  (2022-03-23T06:24:31Z)
• Injecting Semantic Concepts into End-to-End Image Captioning [61.41154537334627]
  We propose a pure vision transformer-based image captioning model, dubbed as ViTCAP, in which grid representations are used without extracting the regional features. For improved performance, we introduce a novel Concept Token Network (CTN) to predict the semantic concepts and then incorporate them into the end-to-end captioning. In particular, the CTN is built on the basis of a vision transformer and is designed to predict the concept tokens through a classification task.
  arXiv  Detail & Related papers  (2021-12-09T22:05:05Z)
• Consensual Collaborative Training And Knowledge Distillation Based Facial Expression Recognition Under Noisy Annotations [2.538209532048867]
  This work proposes an effective training strategy in the presence of noisy labels, called as Consensual Collaborative Training (CCT) framework. CCT co-trains three networks jointly using a convex combination of supervision loss and consistency loss. State-of-the-art performance is reported on the benchmark FER datasets RAFDB (90.84%), FERPlus (89.99%) and AffectNet (66%)
  arXiv  Detail & Related papers  (2021-07-10T03:37:06Z)
• Affect Expression Behaviour Analysis in the Wild using Consensual Collaborative Training [2.538209532048867]
  This report presents Consensual Collaborative Training (CCT) framework used in our submission to the Affective Behaviour Analysis in-the-wild (ABAW) 2021 competition. CCT co-trains three networks jointly using a convex combination of supervision loss and consistency loss. Co-training reduces overall error, and consistency loss prevents overfitting to noisy samples.
  arXiv  Detail & Related papers  (2021-07-08T04:28:21Z)
• Omni-supervised Facial Expression Recognition via Distilled Data [120.11782405714234]
  We propose omni-supervised learning to exploit reliable samples in a large amount of unlabeled data for network training. We experimentally verify that the new dataset can significantly improve the ability of the learned FER model. To tackle this, we propose to apply a dataset distillation strategy to compress the created dataset into several informative class-wise images.
  arXiv  Detail & Related papers  (2020-05-18T09:36:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.