Mean Box Pooling: A Rich Image Representation and Output Embedding for the Visual Madlibs Task
We present Mean Box Pooling, a novel visual representation that pools over CNN representations of a large number, highly overlapping object proposals. We show that such representation together with nCCA, a successful multimodal embedding technique, achieves state-of-the-art performance on the Visual Madlibs task. Moreover, inspired by the nCCA's objective function, we extend classical CNN+LSTM approach to train the network by directly maximizing the similarity between the internal representation of the deep learning architecture and candidate answers. Again, such approach achieves a significant improvement over the prior work that also uses CNN+LSTM approach on Visual Madlibs.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Towards Improved Sentence Representations using Token Graphs
Obtaining a single-vector representation from a Large Language Model's (LLM) token-level outputs is a critical step for nearly all sentence-level tasks. However, standard pooling methods like mean or max aggregation trea…
parameter-efficient fine-tuningGraph Neural NetworkFrom Pixels to Patches: Pooling Strategies for Earth Embeddings
Geospatial foundation models increasingly expose pixel-level embedding products that can be downloaded and reused without access to the underlying encoder. In this setting, downstream tasks with patch- or region-level la…
DePF: A Novel Fusion Approach based on Decomposition Pooling for Infrared and Visible Images
Infrared and visible image fusion aims to generate synthetic images simultaneously containing salient features and rich texture details, which can be used to boost downstream tasks. However, existing fusion methods are s…
DecoderInfrared And Visible Image FusionGlobal Gated Mixture of Second-order Pooling for Improving Deep Convolutional Neural Networks
In most of existing deep convolutional neural networks (CNNs) for classification, global average (first-order) pooling (GAP) has become a standard module to summarize activations of the last convolution layer as final re…
HiRo: A Compact Four-Directional Hierarchical Reservoir Token-Mixer for Efficient Image Classification
Recent image classification models must balance local feature modeling, cross-window interaction, and parameter efficiency. Many high-performing architectures rely on fully trainable token-mixers, which improve represent…
Representation LearningImage Classification