This motivated creation of eProduct, a dataset consisting of 2. 5 million product images towards accelerating development in the areas of self-supervised learning, weakly-supervised learning, and multimodal learning, for fine-grained recognition.
Our contributions include: 1) Designing a Mixed Category Attention Net (MCAN) which integrates both fine-grained and coarse category information into recommendation and learns the compatibility among fashion tuples.
We conduct the learning in an adversarial learning process, which bears a close resemblance to the original GAN but again shifts the learning from image spaces to prior and latent code spaces.
The success of product quantization (PQ) for fast nearest neighbor search depends on the exponentially reduced complexities of both storage and computation with respect to the codebook size.